Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Wu Hao <hao.wu@intel.com>
To:     atull@kernel.org, mdf@kernel.org, linux-fpga@vger.kernel.org,
        linux-kernel@vger.kernel.org
Cc:     linux-api@vger.kernel.org, Wu Hao <hao.wu@intel.com>,
        Ananda Ravuri <ananda.ravuri@intel.com>,
        Xu Yilun <yilun.xu@intel.com>
Subject: [PATCH 03/17] fpga: dfl: fme: support 512bit data width PR
Date:   Mon, 25 Mar 2019 11:07:30 +0800
Message-Id: <1553483264-5379-4-git-send-email-hao.wu@intel.com>
In-Reply-To: <1553483264-5379-1-git-send-email-hao.wu@intel.com>
References: <1553483264-5379-1-git-send-email-hao.wu@intel.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

In early partial reconfiguration private feature, it only
supports 32bit data width when writing data to hardware for
PR. 512bit data width PR support is an important optimization
for some specific solutions (e.g. XEON with FPGA integrated),
it allows driver to use AVX512 instruction to improve the
performance of partial reconfiguration. e.g. programming one
100MB bitstream image via this 512bit data width PR hardware
only takes ~300ms, but 32bit revision requires ~3s per test
result.

Please note now this optimization is only done on revision 2
of this PR private feature which is only used in integrated
solution that AVX512 is always supported.

Signed-off-by: Ananda Ravuri <ananda.ravuri@intel.com>
Signed-off-by: Xu Yilun <yilun.xu@intel.com>
Signed-off-by: Wu Hao <hao.wu@intel.com>
---
 drivers/fpga/dfl-fme-main.c |  3 ++
 drivers/fpga/dfl-fme-mgr.c  | 75 +++++++++++++++++++++++++++++++++++++--------
 drivers/fpga/dfl-fme-pr.c   | 45 ++++++++++++++++-----------
 drivers/fpga/dfl-fme.h      |  2 ++
 drivers/fpga/dfl.h          |  5 +++
 5 files changed, 99 insertions(+), 31 deletions(-)

diff --git a/drivers/fpga/dfl-fme-main.c b/drivers/fpga/dfl-fme-main.c
index 086ad24..076d74f 100644
--- a/drivers/fpga/dfl-fme-main.c
+++ b/drivers/fpga/dfl-fme-main.c
@@ -21,6 +21,8 @@
 #include "dfl.h"
 #include "dfl-fme.h"
 
+#define DRV_VERSION	"0.8"
+
 static ssize_t ports_num_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
@@ -277,3 +279,4 @@ MODULE_DESCRIPTION("FPGA Management Engine driver");
 MODULE_AUTHOR("Intel Corporation");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("platform:dfl-fme");
+MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/fpga/dfl-fme-mgr.c b/drivers/fpga/dfl-fme-mgr.c
index b3f7eee..027d457 100644
--- a/drivers/fpga/dfl-fme-mgr.c
+++ b/drivers/fpga/dfl-fme-mgr.c
@@ -22,14 +22,18 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/fpga/fpga-mgr.h>
 
+#include "dfl.h"
 #include "dfl-fme-pr.h"
 
+#define DRV_VERSION	"0.8"
+
 /* FME Partial Reconfiguration Sub Feature Register Set */
 #define FME_PR_DFH		0x0
 #define FME_PR_CTRL		0x8
 #define FME_PR_STS		0x10
 #define FME_PR_DATA		0x18
 #define FME_PR_ERR		0x20
+#define FME_PR_512_DATA		0x40 /* Data Register for 512bit datawidth PR */
 #define FME_PR_INTFC_ID_L	0xA8
 #define FME_PR_INTFC_ID_H	0xB0
 
@@ -67,8 +71,31 @@
 #define PR_WAIT_TIMEOUT   8000000
 #define PR_HOST_STATUS_IDLE	0
 
+#if defined(CONFIG_X86) && defined(CONFIG_AS_AVX512)
+
+#include <asm/fpu/api.h>
+
+static inline void copy512(void *src, void __iomem *dst)
+{
+	kernel_fpu_begin();
+
+	asm volatile("vmovdqu64 (%0), %%zmm0;"
+		     "vmovntdq %%zmm0, (%1);"
+		     :
+		     : "r"(src), "r"(dst));
+
+	kernel_fpu_end();
+}
+#else
+static inline void copy512(void *src, void __iomem *dst)
+{
+	WARN_ON_ONCE(1);
+}
+#endif
+
 struct fme_mgr_priv {
 	void __iomem *ioaddr;
+	unsigned int pr_datawidth;
 	u64 pr_error;
 };
 
@@ -169,7 +196,7 @@ static int fme_mgr_write(struct fpga_manager *mgr,
 	struct fme_mgr_priv *priv = mgr->priv;
 	void __iomem *fme_pr = priv->ioaddr;
 	u64 pr_ctrl, pr_status, pr_data;
-	int delay = 0, pr_credit, i = 0;
+	int ret = 0, delay = 0, pr_credit;
 
 	dev_dbg(dev, "start request\n");
 
@@ -181,9 +208,9 @@ static int fme_mgr_write(struct fpga_manager *mgr,
 
 	/*
 	 * driver can push data to PR hardware using PR_DATA register once HW
-	 * has enough pr_credit (> 1), pr_credit reduces one for every 32bit
-	 * pr data write to PR_DATA register. If pr_credit <= 1, driver needs
-	 * to wait for enough pr_credit from hardware by polling.
+	 * has enough pr_credit (> 1), pr_credit reduces one for every pr data
+	 * width write to PR_DATA register. If pr_credit <= 1, driver needs to
+	 * wait for enough pr_credit from hardware by polling.
 	 */
 	pr_status = readq(fme_pr + FME_PR_STS);
 	pr_credit = FIELD_GET(FME_PR_STS_PR_CREDIT, pr_status);
@@ -192,7 +219,8 @@ static int fme_mgr_write(struct fpga_manager *mgr,
 		while (pr_credit <= 1) {
 			if (delay++ > PR_WAIT_TIMEOUT) {
 				dev_err(dev, "PR_CREDIT timeout\n");
-				return -ETIMEDOUT;
+				ret = -ETIMEDOUT;
+				goto done;
 			}
 			udelay(1);
 
@@ -200,21 +228,32 @@ static int fme_mgr_write(struct fpga_manager *mgr,
 			pr_credit = FIELD_GET(FME_PR_STS_PR_CREDIT, pr_status);
 		}
 
-		if (count < 4) {
+		if (count < priv->pr_datawidth) {
 			dev_err(dev, "Invalid PR bitstream size\n");
 			return -EINVAL;
 		}
 
-		pr_data = 0;
-		pr_data |= FIELD_PREP(FME_PR_DATA_PR_DATA_RAW,
-				      *(((u32 *)buf) + i));
-		writeq(pr_data, fme_pr + FME_PR_DATA);
-		count -= 4;
+		switch (priv->pr_datawidth) {
+		case 4:
+			pr_data = 0;
+			pr_data |= FIELD_PREP(FME_PR_DATA_PR_DATA_RAW,
+					*((u32 *)buf));
+			writeq(pr_data, fme_pr + FME_PR_DATA);
+			break;
+		case 64:
+			copy512((void *)buf, fme_pr + FME_PR_512_DATA);
+			break;
+		default:
+			ret = -EFAULT;
+			goto done;
+		}
+		buf += priv->pr_datawidth;
+		count -= priv->pr_datawidth;
 		pr_credit--;
-		i++;
 	}
 
-	return 0;
+done:
+	return ret;
 }
 
 static int fme_mgr_write_complete(struct fpga_manager *mgr,
@@ -302,6 +341,15 @@ static int fme_mgr_probe(struct platform_device *pdev)
 			return PTR_ERR(priv->ioaddr);
 	}
 
+	/*
+	 * Only revision 2 supports 512bit datawidth for better performance,
+	 * other revisions use default 32bit datawidth.
+	 */
+	if (dfl_feature_revision(priv->ioaddr) == 2)
+		priv->pr_datawidth = 64;
+	else
+		priv->pr_datawidth = 4;
+
 	compat_id = devm_kzalloc(dev, sizeof(*compat_id), GFP_KERNEL);
 	if (!compat_id)
 		return -ENOMEM;
@@ -342,3 +390,4 @@ MODULE_DESCRIPTION("FPGA Manager for DFL FPGA Management Engine");
 MODULE_AUTHOR("Intel Corporation");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("platform:dfl-fme-mgr");
+MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/fpga/dfl-fme-pr.c b/drivers/fpga/dfl-fme-pr.c
index c1fb1fe..8a0e46a 100644
--- a/drivers/fpga/dfl-fme-pr.c
+++ b/drivers/fpga/dfl-fme-pr.c
@@ -83,7 +83,7 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg)
 	if (copy_from_user(&port_pr, argp, minsz))
 		return -EFAULT;
 
-	if (port_pr.argsz < minsz || port_pr.flags)
+	if (port_pr.argsz < minsz || port_pr.flags || !port_pr.buffer_size)
 		return -EINVAL;
 
 	/* get fme header region */
@@ -101,15 +101,25 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg)
 		       port_pr.buffer_size))
 		return -EFAULT;
 
+	mutex_lock(&pdata->lock);
+	fme = dfl_fpga_pdata_get_private(pdata);
+	/* fme device has been unregistered. */
+	if (!fme) {
+		ret = -EINVAL;
+		goto unlock_exit;
+	}
+
 	/*
 	 * align PR buffer per PR bandwidth, as HW ignores the extra padding
 	 * data automatically.
 	 */
-	length = ALIGN(port_pr.buffer_size, 4);
+	length = ALIGN(port_pr.buffer_size, fme->pr_datawidth);
 
 	buf = vmalloc(length);
-	if (!buf)
-		return -ENOMEM;
+	if (!buf) {
+		ret = -ENOMEM;
+		goto unlock_exit;
+	}
 
 	if (copy_from_user(buf,
 			   (void __user *)(unsigned long)port_pr.buffer_address,
@@ -127,18 +137,10 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg)
 
 	info->flags |= FPGA_MGR_PARTIAL_RECONFIG;
 
-	mutex_lock(&pdata->lock);
-	fme = dfl_fpga_pdata_get_private(pdata);
-	/* fme device has been unregistered. */
-	if (!fme) {
-		ret = -EINVAL;
-		goto unlock_exit;
-	}
-
 	region = dfl_fme_region_find(fme, port_pr.port_id);
 	if (!region) {
 		ret = -EINVAL;
-		goto unlock_exit;
+		goto free_exit;
 	}
 
 	fpga_image_info_free(region->info);
@@ -159,13 +161,10 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg)
 		fpga_bridges_put(&region->bridge_list);
 
 	put_device(&region->dev);
-unlock_exit:
-	mutex_unlock(&pdata->lock);
 free_exit:
 	vfree(buf);
-	if (copy_to_user((void __user *)arg, &port_pr, minsz))
-		return -EFAULT;
-
+unlock_exit:
+	mutex_unlock(&pdata->lock);
 	return ret;
 }
 
@@ -391,6 +390,16 @@ static int pr_mgmt_init(struct platform_device *pdev,
 	mutex_lock(&pdata->lock);
 	priv = dfl_fpga_pdata_get_private(pdata);
 
+	/*
+	 * Initialize PR data width.
+	 * Only revision 2 supports 512bit datawidth for better performance,
+	 * other revisions use default 32bit datawidth.
+	 */
+	if (dfl_feature_revision(feature->ioaddr) == 2)
+		priv->pr_datawidth = 64;
+	else
+		priv->pr_datawidth = 4;
+
 	/* Initialize the region and bridge sub device list */
 	INIT_LIST_HEAD(&priv->region_list);
 	INIT_LIST_HEAD(&priv->bridge_list);
diff --git a/drivers/fpga/dfl-fme.h b/drivers/fpga/dfl-fme.h
index 5394a21..de20755 100644
--- a/drivers/fpga/dfl-fme.h
+++ b/drivers/fpga/dfl-fme.h
@@ -21,12 +21,14 @@
 /**
  * struct dfl_fme - dfl fme private data
  *
+ * @pr_datawidth: data width for partial reconfiguration.
  * @mgr: FME's FPGA manager platform device.
  * @region_list: linked list of FME's FPGA regions.
  * @bridge_list: linked list of FME's FPGA bridges.
  * @pdata: fme platform device's pdata.
  */
 struct dfl_fme {
+	int pr_datawidth;
 	struct platform_device *mgr;
 	struct list_head region_list;
 	struct list_head bridge_list;
diff --git a/drivers/fpga/dfl.h b/drivers/fpga/dfl.h
index a8b869e..8851c6c 100644
--- a/drivers/fpga/dfl.h
+++ b/drivers/fpga/dfl.h
@@ -331,6 +331,11 @@ static inline bool dfl_feature_is_port(void __iomem *base)
 		(FIELD_GET(DFH_ID, v) == DFH_ID_FIU_PORT);
 }
 
+static inline u8 dfl_feature_revision(void __iomem *base)
+{
+	return (u8)FIELD_GET(DFH_REVISION, readq(base + DFH));
+}
+
 /**
  * struct dfl_fpga_enum_info - DFL FPGA enumeration information
  *
-- 
2.7.4